Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods
David H. Haussler, Michael J. Kearns, Manfred Opper, Robert E. Schapire · Neural Information Processing Systems · 1991
In this paper we investigate an average-case model of concept learning, and give results that place the popular statistical physics and VC dimension theories of learning curve behavior in a common framework.